U.S. patent application number 17/603389 was filed with the patent office on 2022-07-07 for method and system for controlling a quantity of a wind turbine by choosing the controller via machine learning.
The applicant listed for this patent is CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE, IFP Energies nouvelles, INSTITUT POLYTECHNIQUE DE GRENOBLE, UNIVERSITE GRENOBLE ALPES. Invention is credited to Mazen AL-AMIR, David COLLET, Domenico DI DOMENICO, Guillaume SABIRON.
Application Number | 20220213868 17/603389 |
Document ID | / |
Family ID | |
Filed Date | 2022-07-07 |
United States Patent
Application |
20220213868 |
Kind Code |
A1 |
COLLET; David ; et
al. |
July 7, 2022 |
METHOD AND SYSTEM FOR CONTROLLING A QUANTITY OF A WIND TURBINE BY
CHOOSING THE CONTROLLER VIA MACHINE LEARNING
Abstract
The present invention relates to a method of controlling a wind
turbine by automatic online selection of a controller that
minimizes the wind turbine fatigue. The method therefore relies on
an (offline constructed) database (BDD) of simulations of a list
(LIST) of controllers, and on an online machine learning step for
determining the optimal controller in terms of wind turbine (EOL)
fatigue. Thus, the method allows automatic selection of controllers
online, based on a fatigue criterion, and switching between the
controllers according to the measured evolution of wind
condition.
Inventors: |
COLLET; David;
(RUEIL-MALMAISON CEDEX, FR) ; SABIRON; Guillaume;
(RUEIL-MALMAISON CEDEX, FR) ; DI DOMENICO; Domenico;
(RUEIL-MALMAISON CEDEX, FR) ; AL-AMIR; Mazen;
(SAINT MARTIN D'HERES, FR) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
IFP Energies nouvelles
CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE
UNIVERSITE GRENOBLE ALPES
INSTITUT POLYTECHNIQUE DE GRENOBLE |
RUEIL-MALMAISON CEDEX
PARIS CEDEX 16
SAINT MARTIN D'HERES
GRENOBLE CEDEX 1 |
|
FR
FR
FR
FR |
|
|
Appl. No.: |
17/603389 |
Filed: |
March 27, 2020 |
PCT Filed: |
March 27, 2020 |
PCT NO: |
PCT/EP2020/058739 |
371 Date: |
October 13, 2021 |
International
Class: |
F03D 7/02 20060101
F03D007/02; F03D 7/04 20060101 F03D007/04 |
Foreign Application Data
Date |
Code |
Application Number |
Apr 16, 2019 |
FR |
FR1904071 |
Claims
1.-10. (canceled)
11. A method of controlling a quantity of a wind turbine for which
a list of plural controllers of the quantity of the wind turbine is
available, comprising steps of: a) constructing a database offline
by simulating, for each controller of the list and for plural wind
data, a cost function representative of fatigue of the wind
turbine; b) measuring wind data online; c) determining online a
controller from the list that minimizes fatigue of wind turbine for
the measured wind data by machine learning from the database; and
d) controlling online the quantity of the wind turbine by use of
the determined controller.
12. A control method as claimed in claim 11, wherein the plural
controllers of the list are selected from among proportional
integral PI controllers, at least one of Hoc regulators with
different weighting functions, and linear quadratic regulators with
different weightings, and model predictive controls with different
weightings and LiDAR-based predictive controls.
13. A control method as claimed in claim 11, wherein the machine
learning is implemented by a regression method predicting the
fatigue of the wind turbine for each controller of the list or by
use of a method of classifying the controllers of the list that
minimizes cost criterion according to the measured wind data.
14. A control method as claimed in claim 12, wherein the machine
learning is implemented by a regression method predicting the
fatigue of the wind turbine for each controller of the list or by
use of a method of classifying the controllers of the list that
minimizes cost criterion according to the measured wind data.
15. A control method as claimed in claim 13, wherein the machine
learning is implemented by use of a regression method carrying out
steps of: i) the measured wind data; ii) performing a polynomial
increase in the measured wind data; and iii) performing a linear
regression of the polynomially increased wind data by use of a
change in space of a target value.
16. A control method as claimed in claim 14, wherein the machine
learning is implemented by use of a regression method carrying out
steps of: i) the measured wind data; ii) performing a polynomial
increase in the measured wind data; and iii) performing a linear
regression of the polynomially increased wind data by use of a
change in space of a target value.
17. A control method as claimed in claim 13, wherein the machine
learning is implemented by use of a regression method based on a
random forest method, a neural network method, a support vector
machine method or a Gaussian process method.
18. A control method as claimed in claim 14, wherein the machine
learning is implemented by use of a regression method based on a
random forest method, a neural network method, a support vector
machine method or a Gaussian process method.
19. A control method as claimed in claim 11, wherein an individual
angle or the individual pitch of at least one blade of the wind
turbine is controlled.
20. A control method as claimed in claim 12, wherein an individual
angle or the individual pitch of at least one blade of the wind
turbine is controlled.
21. A control method as claimed in claim 13, wherein an individual
angle or the individual pitch of at least one blade of the wind
turbine is controlled.
22. A control method as claimed in claim 14, wherein an individual
angle or the individual pitch of at least one blade of the wind
turbine is controlled.
23. A control method as claimed in claim 11, wherein the
controllers of the list further account for a regulation error
between a setpoint for regulating the quantity of the wind turbine
and a measurement of the quantity of the wind turbine.
24. A control method as claimed in claim 11, wherein the wind data
used for constructing the database results from measurements on the
site of the wind turbine.
25. A control method as claimed in claim 11, wherein the wind data
used for constructing the database is provided by a wind
simulator.
26. A control method as claimed in claim 12, wherein the wind data
used for constructing the database is provided by a wind
simulator.
27. A control method as claimed in claim 13, wherein the wind data
used for constructing the database is provided by a wind
simulator.
28. A control method as claimed in claim 14, wherein the wind data
used for constructing the database is provided by a wind
simulator.
29. A control method as claimed in claim 15, wherein the wind data
used for constructing the database is provided by a wind
simulator.
30. A system for controlling a quantity of a wind turbine using the
control method as claimed in claim 11, the control system
comprising means for storing the controller list and the database
constructed by simulating for plural wind data a cost function
representative of fatigue of the wind turbine for each controller
of the list, means for measuring wind data, means for determining a
controller of the list that minimizes fatigue of the wind turbine
for the measured wind data by machine learning from the database,
and for controlling the quantity of the wind turbine.
Description
CROSS REFERENCE TO RELATED APPLICATIONS
[0001] Reference is made to PCT/EP2020/058739 filed Mar. 27, 2020,
designating the United States, and French Application No. 1904.071
filed Apr. 16, 2019, which are incorporated herein by reference in
their entirety.
BACKGROUND OF THE INVENTION
Field of the Invention
[0002] The present invention relates to the field of wind turbine
control, in particular to the control of the individual inclination
angle or the individual pitch of at least one blade of a wind
turbine.
Description of the Prior Art
[0003] A wind turbine allows the kinetic energy from the wind to be
converted into electrical or mechanical energy. For conversion of
wind to electrical energy, it is made up of the following
elements:
[0004] a tower for positioning a rotor at a sufficient height to
enable motion thereof (necessary for horizontal-axis wind turbines)
or allowing the rotor to be positioned at a height enabling it to
be driven by a stronger and more regular wind than at ground level.
The tower generally houses part of the electrical and electronic
components (modulator, control, multiplier, generator, etc.);
[0005] a nacelle mounted at the top of the tower, housing
mechanical, pneumatic and some electrical and electronic components
necessary to operate the turbine. The nacelle can rotate so as to
orient the machine in the right direction;
[0006] a rotor fastened to the nacelle, comprising blades
(generally three) and the hub of the wind turbine. The rotor is
driven by the wind energy and it is connected by a mechanical
shaft, directly or indirectly (via a gearbox and mechanical shaft
system), to an electric machine (electric generator) that converts
the energy recovered to electrical energy. The rotor is potentially
provided with control systems such as variable-angle blades or
aerodynamic brakes; and
[0007] a transmission made up of two shafts (mechanical shaft of
the rotor and mechanical shaft of the electrical machine) connected
by a transmission (gearbox).
[0008] Since the early 1990s, there has been renewed interest in
wind power, in particular in the European Union where the annual
growth rate is about 20%. This growth is related to the inherent
possibility for carbon-free electricity generation. Furthermore, in
view of the objectives set during COP21, a net decarbonization of
the energy should take place in the upcoming century. Wind energy
appears as one of the most mature renewable energies for the
upcoming energy transition, as evidenced by the growth of its
installed power capacity, which should continue to increase for
several more decades. The wind energy industry already represents
several hundred billion euros and it should continue to grow,
therefore a decrease in the wind energy production costs can enable
savings of several hundred million or even billions of euros. In
addition, in order to maximize energy production, the wind industry
tends to increase the diameter of the rotor, which causes an
increase in mechanical loads on the blades and the rotor. In order
to sustain this growth, the energy yield of wind turbines still
needs to be further improved. The prospect of wind power production
increase requires developing effective production tools and
advanced control tools in order to improve the performances of the
machines. All wind turbines are therefore designed with a power
regulation system.
[0009] For this power regulation, controllers have been designed
for variable-speed aerogenerators. The purpose of the controllers
is to maximize the electrical power recovered, to minimize the
rotor speed fluctuations, and to minimize the fatigue and the
extreme moments of the structure (blades, tower and platform).
[0010] Control of the variable-speed wind turbines has therefore
been divided into three categories: [0011] yaw control (control of
the wind turbine orientation with respect to the wind) [0012]
generator torque control (maximization of the turbine power when
the wind is below the nominal speed allowed by the turbine) [0013]
blade pitch control (regulation of the aerodynamic torque of the
turbine when the wind is above the nominal value by inclination of
the blades).
[0014] The blade control can itself be divided into two control
strategy types, collective pitch control (CPC) where each blade has
the same inclination angle and individual pitch control (TPC) where
each blade has a different inclination angle. The main purpose of
CPC is to control the aerodynamic torque of the wind turbine so as
not to switch to overspeed, which may combine with an objective of
controlling the thrust force on the rotor.
[0015] CPC considers an average wind passing through the rotor and
therefore assumes that the wind is uniform over the surface of the
rotor. This assumption is less and less true due to the constant
increase in diameter of the rotors produced (which can be up to 200
m). IPC is notably described in the following documents:
[0016] Bossanyi, E. (2003). Individual Blade Pitch Control for Load
Reduction. Wind. Energy, 119-128,
[0017] Schlipf, D. (2010). Look-Ahead Cyclic Pitch Control Using
LiDAR. The science of making torque from wind,
[0018] Burton, T. (2011). Wind Energy Handbook.,
[0019] Lu, Q., Bowyer, R., & Jones, B. L. (2015). Analysis and
Design of Coleman Transform-Based Individual Pitch Controllers for
Wind-Turbine Load Reduction. Wind Energy, 1451-1468.
[0020] In these works, IPC is considered with the Coleman transform
(Coleman, R. P., & Feingold, A. M. (1957). Theory of
self-excited mechanical oscillations of helicopter rotors with
hinged blades. National Advisory Committee for Aeronautics), which
makes it possible to switch from the rotating reference frame of
the blades to the fixed reference frame of the wind turbine hub. By
means of this transformation, the out-of-plane moments on each
blade are transformed into pitch and yaw moments on the hub, which
reflects an imbalance of the aerodynamic loads on the wind turbine
blades. Most often, IPC is used in addition to CPC (Burton, 2011;
Bossanyi, 2003; Lu, Bowyer, & Jones, 2015; Schlipf, 2010), and
the IPC controller gives an angle offset on each blade, such that
the sum of the angle offsets is zero, which enables the IPC not to
disturb proper CPC control (Burton, 2011). To date, a single
controller jointly synthesizing CPC and IPC controls (Ranch, S.,
& Schlipf, D. (2014). Nonlinear model predictive control of
floating wind turbines with individual pitch control. American
Control Conference (ACC), (pp. 4434-4439)) has been proposed in the
literature.
[0021] Assessing the service life or the fatigue of a wind turbine
is a complex process because the signals resulting from simulations
need to be analysed via a counting algorithm and by applying the
Palmgren-Miner rule (Miner, M. (1945). Cumulative Damage. Fatigue
Journal of Applied Mechanics), which relates the loading cycles to
the consumed life fraction of the component. The count is not the
result of a simple algebraic function, but of an algorithm known as
rainflow counting (RFC (Downing & Socie, 1982)) algorithm. This
counting makes the expression of fatigue discontinuous and
non-integrable over time. On the other hand, several works have
presented techniques for fatigue prediction as a function of the
wind characteristics for a wind turbine with a given closed-loop
controller (Dimitrov, N., & Kelly, M. (2018). From wind to
loads: wind turbine site-specific load estimation using databases
with high-fidelity load simulations. Wind Energy Science
Discussions; Murcia, J., Rethore, P., & Dimitrov, N. (2017).
Uncertainty propagation through an aeroelastic wind turbine model
using polynomial surrogates. Renewable Energy, 910-922). A study
has shown that the winds that may be experienced by a wind farm can
be grouped into different wind types (Clifton, A., & Schreck,
S. (2013). Turbine Inflow Characterization at the National Wind
Technology Center. Journal of Solar Energy Engineering). These wind
types evolve as a function of the climate variations between day
and night (due to the sunshine and temperature differences) and
from day to day (due to the movements of air masses on the earth's
surface). The characteristics of the wind therefore evolve
slowly.
[0022] Furthermore, various control methods have been developed to
improve energy recovery while limiting wind turbine fatigue.
Fatigue could be used as an objective function in a conventional
optimal control technique, but the specificities of the
aforementioned fatigue calculation and counting algorithm used make
this use very complex. In order to overcome this complexity, the
fatigue is often approximated with integrals of quadratic
functions; however, although the integral of a quadratic function
allows the fatigue to be considered qualitatively, it does not
allow it to be considered quantitatively (Knudsen, Bak &
Svenstrup, 2015). It is important to consider the amount of fatigue
on various elements of a wind turbine because it makes it possible
to better weight the compromise between their fatigues. One work
notably aimed at minimizing the fatigue by adapting the weights of
a model predictive control MPC so that the quadratic cost function
reflects the fatigue (Barradas & Wisniewski, 2016).
[0023] Among these control methods, patent application FR-2,976,630
corresponding to U.S. Pat. No. 10,041,473 relates to a method for
optimizing the electrical energy production of a horizontal-axis
wind turbine, by performing a non-linear control of the blade
orientation taking account of the system dynamics, while minimizing
the mechanical impact on the structure. The impact is minimized by
modifying the inclination angle of the blades in such a way that
the aerodynamic force applied onto the nacelle leads to a zero
speed at the tower top. The method notably relies on a physical
model of the aerodynamic force.
[0024] Besides, patent application FR-2,988,442 corresponding to
U.S. Pat. No. 9,458,826 relates to a method for controlling an
inclination angle of the blades by carrying out the following
steps: [0025] a) determining an aerodynamic torque setpoint and a
torque setpoint for the electrical machine allowing to maximize the
recovered power, from wind speed, rotor speed and electrical
machine speed measurements; [0026] b) modifying at least one of the
setpoints by subtracting therefrom a term proportional to a
difference between the measured rotor speed and the measured
electrical machine speed; [0027] c) determining an inclination
angle for the blades allowing the aerodynamic torque setpoint to be
achieved; and [0028] d) orienting the blades according to the
inclination angle.
[0029] However, the methods described in the prior art are not
entirely satisfactory in terms of control optimization by reducing
the wind turbine fatigue, in particular for all wind conditions,
notably because they do not consider the overall wind turbine
fatigue reduction as an objective function.
SUMMARY OF THE INVENTION
[0030] In order to minimize the impact of wind on the fatigue of a
wind turbine, the present invention relates to a method of
controlling a quantity of a wind turbine by automated online
selection of a controller that minimizes the wind turbine fatigue.
The method therefore relies on an (offline constructed) database of
simulations of a list of controllers, and on an online machine
learning step for determining the optimal controller in terms of
wind turbine fatigue. Thus, the method allows automatic selection
of controllers online, based on a fatigue criterion, and to switch
between the controllers according to the measured evolutions of
wind condition.
[0031] The invention relates to a method of controlling a quantity
of a wind turbine for which a list of controllers of the quantity
of the wind turbine is available, wherein the following steps are
carried out: [0032] a) constructing a database offline by
simulating, for each controller of the list and for plural wind
data, a cost function representative of the fatigue of the wind
turbine; [0033] b) measuring wind data online; [0034] c)
determining online a controller of the list that minimizes the
fatigue of the wind turbine for the measured wind data by machine
learning from the database; and [0035] d) controlling online the
quantity of the wind turbine by use of the determined
controller.
[0036] According to one embodiment, the plural controllers of the
list are selected from among proportional integral PI controllers,
and H.infin. regulators with at least one of the different
weighting functions, and linear quadratic regulators LQR with
different weightings, and model predictive controls MPC with
different weightings and LiDAR-based predictive controls.
[0037] According to one implementation, the machine learning is
implemented by use of a regression method predicting the fatigue of
the wind turbine for each controller of the list or by use of a
method of classifying the controllers of the list that minimize the
cost criterion according to the measured wind data.
[0038] Advantageously, the machine learning is implemented by use
of a regression method by carrying out the following steps: [0039]
i) standardizing the measured wind data; [0040] ii) performing a
polynomial increase in the measured wind data; and [0041] iii)
performing a linear regression of the polynomially increased wind
data by use of a change in space of the target value.
[0042] Alternatively, the machine learning is implemented by a
regression method based on a random forest method, a neural network
method, a support vector machine method or a Gaussian process
method.
[0043] According to one aspect, the individual angle or the
individual pitch of at least one blade of the wind turbine is
controlled.
[0044] According to one option, the controllers of the list further
take account for a regulation error between a setpoint for
regulating the quantity of the wind turbine and a measurement of
the quantity of the wind turbine.
[0045] According to a feature, the wind data used for constructing
the database results from measurements on the site of the wind
turbine.
[0046] According to one embodiment, the wind data used for
constructing the database comes from a wind simulator.
[0047] Moreover, the invention relates to a system of controlling a
quantity of a wind turbine using the control method according to
one of the above features, the control system comprising means for
storing the controller list and the database constructed by
simulating for plural wind data a cost function representative of
the fatigue of the wind turbine for each controller of the list,
wind data measurement, means for determining a controller of the
list that minimizes the fatigue of the wind turbine for the
measured wind data by machine learning from the database, and means
for controlling the quantity of the wind turbine.
BRIEF DESCRIPTION OF THE FIGURES
[0048] Other features and advantages of the method according to the
invention will be clear from reading the description hereafter of
embodiments given by way of non-imitative example, with reference
to the accompanying figures wherein:
[0049] FIG. 1 illustrates the steps of the control method according
to an embodiment of the invention;
[0050] FIG. 2 illustrates the regression machine learning step
according to a variant embodiment of the invention; and
[0051] FIG. 3 is a curve of the real and the estimated fatigue
values for an example embodiment of the invention.
DETAILED DESCRIPTION OF THE INVENTION
[0052] The invention relates to a method of controlling a quantity
of a wind turbine in order to minimize the fatigue of the wind
turbine or of at least a part of the wind turbine (that is a wind
turbine component) according to measured wind data. The method
according to the invention is based on the selection of the optimal
controller (in terms of fatigue) by machine learning. The principle
develops a learning algorithm allowing construction of a map
relating measured wind conditions to a mechanical fatigue quantity.
One of the goals of the invention can be to create a substitution
model for estimating the service life of the wind turbine in a wind
farm with an almost instantly given wind distribution.
[0053] In the rest of the description, the expression "wind turbine
fatigue" also designates the fatigue of at least one turbine
component.
[0054] A wind turbine quantity is understood to be any parameter of
the wind turbine that can be controlled. According to a preferred
embodiment, the quantity can be the individual inclination angle or
the individual pitch of the blades used in the individual pitch
control TPC.
[0055] Wind data is understood to be information relative to the
incoming wind. This wind data can be measured notably by a LiDAR
(laser imaging, detection and ranging) sensor, an anemometer or a
SODAR (sonic detection and ranging) sensor, etc. By way of
non-limitative example, wind data can notably comprise the
following information: mean and standard deviation of the rotor
averaged wind speed, horizontal and vertical gradients of the rotor
averaged wind speed, pitch and yaw misalignments, rotor averaged
wind turbulence intensity.
[0056] In order to select the optimal turbine quantity control, the
method is based on the use of a predetermined list of a plural
controllers (at least two controllers). Using plural controllers
provides control adaptability to different wind conditions and it
therefore enables optimal control whatever the wind conditions. The
plural controllers of the list can be selected from among
proportional integral PI controllers, and/or H.infin. D regulators
with different weighting functions, and at least one of linear
quadratic regulators LQR, and model predictive controls MPC and/or
LiDAR-based predictive controls with different weightings. The
controller list can comprise controllers of the same type, that is
several differently parametrized controllers.
[0057] The method according to the invention can then combine three
aspects: control of a quantity of the wind turbine (individual
blade control for example), wind characteristics that evolve slowly
and turbine fatigue prediction. Substitution model techniques for
fatigue can be used to predict a cost for the wind turbine
subjected to the current wind for different controllers of a
discrete set. This enables automatic online selection of the
controllers, based on a fatigue criterion, and control of the wind
turbine quantity by switching between controllers according to the
wind condition evolutions.
[0058] The method according to the invention comprises the
following steps:
[0059] 1) database construction;
[0060] 2) wind data measurement;
[0061] 3) determining the controller by machine learning; and
[0062] 4) controlling the wind turbine quantity.
[0063] Step 1) is carried out offline beforehand to limit the
duration of the online control process. Moreover, the highest
calculation cost of the method according to the invention is thus
related to a step carried out offline.
[0064] Steps 2) to 4) are carried out online during operation of
the wind turbine for real-time selection of the controller.
[0065] FIG. 1 schematically illustrates, by way of non-limitative
example, the steps of the method according to one embodiment of the
invention. A list LIST of controllers of the wind turbine quantity
is determined beforehand. From this controller list LIST, and by
use of simulations, database BDD representative of the turbine
fatigue is constructed offline for the controllers of list LIST and
for wind data. Wind data X is measured online. This measured wind
data X, controller list LIST and database BDD are then used by a
high-level controller CHN to determine, online, a controller K* of
list LIST that minimizes the turbine fatigue for the measured wind
data X. This determination of controller K* is performed by machine
learning.
[0066] The determined controller K* is then used for online control
CONT of the wind turbine quantity. In the embodiment illustrated,
control CONT is carried out by considering a regulation error E
corresponding to the difference between the regulation setpoint r
of the turbine quantity and a measurement y of the turbine quantity
y. Control CONT then generates a control signal u (an individual
blade pitch for example) for wind turbine EOL. According to an
embodiment option, regulation setpoint r can be, in most cases,
zero so that the control, notably control IPC, can regulate the
loads that unbalance the wind turbine to 0. In a variant, notably
in the case of floating wind turbines, setpoint r can be given by
an external controller for stabilizing and/or balancing the
turbine.
[0067] The steps of the control method are detailed in the rest of
the description.
[0068] 1. Database Construction
[0069] in this step, a database is constructed offline by
simulating, for each controller of the predetermined list and for a
plural wind data, a cost function representative of the wind
turbine fatigue.
[0070] According to one embodiment of the invention, the plural
wind data used for this step can be obtained by use of preliminary
measurements on the wind turbine site. Thus, the database will be
as representative as possible.
[0071] Alternatively, the plural wind data used for this step can
be obtained by a wind simulator, for example the TurbSim.TM.
software (NREL, National Renewable Energy Laboratory), which is a
stochastic full-field turbulence simulator.
[0072] Simulation of the turbine behavior can be performed by a
numerical simulator, for example an aeroelastic wind turbine
simulator such as the FAST.TM. software (NREL, National Renewable
Energy Laboratory).
[0073] A cost criterion J, whose complexity is not a limitation
since it is assessed offline, is then designed. Typically, it is
possible to use complex fatigue models of the mechanical elements
of the turbine in order to have a cost criterion true to the damage
undergone by the turbine. These models are most often not usable
online because a rather long time series is necessary to evaluate
the fatigue with these models. Thus, one advantage of the method
according to the invention is that it can use complex turbine
fatigue cost models that cannot be used directly online.
[0074] According to an implementation of the invention, the fatigue
model can be a Palmgren-Miner model that counts the number of
loading and unloading hysteresis loops. This counting may be
discontinuous. Preferably, the counting method can be the rainflow
counting method RFC. These counting methods do not allow fatigue to
be expressed as the integral of an algebraic loading function,
which is conventionally used in optimal control (cost of the
integrals of quadratic functions). The integral of a quadratic cost
function does not enable evaluation of the number of fatigue
cycles, which is a problem when a compromise is to be assessed
between the fatigues of various elements. One of the main
advantages of the method according to the invention is to make it
possible to integrate the fatigue calculation in the global control
strategy.
[0075] Each simulation is evaluated with the previously designed
cost criterion J. Thus, the simulation of the wind turbine
subjected to the wind i, denoted by in a closed loop with
controller K.sub.j belonging to the list K.sub.list, has a cost
y.sub.ij=J(w.sub.i,K.sub.j). On the other hand, in order to reduce
the number of variables and to simplify the problem, it is possible
to extract from the wind measurements characteristics capable of
unequivocally characterizing wind woo and which could be correlated
with the value of the cost criterion. Function g giving, from wind
the wind characteristic vector X.sub.i=g(w.sub.i) can then be
defined.
[0076] 2. Wind Data Measurement
[0077] In this step, the wind data is measured online to know the
incoming wind in real time.
[0078] According to one embodiment, these measurements can be
carried out by a LiDAR sensor.
[0079] 3. Determining the Controller by Machine Learning
[0080] This step determines online the optimal controller in terms
of wind turbine fatigue for the wind data measured in the previous
step. The controller is determined from among the controller list
by machine teaming using the database constructed in step 1) and
the wind data measurements of step 2), as well as the controller
list.
[0081] According to one implementation of the invention, two ways
of combining the data and machine learning for selecting the
controllers can be considered: cost prediction via regression
techniques (one regression per controller in the list) and
classification of the controllers that minimize the cost criterion
according to the current wind (measured wind data).
[0082] According to a first embodiment, the regression can
reconstruct the map J(w.sub.i,K.sub.j)=(g(w.sub.i),
K.sub.j)=(X.sub.i, K.sub.j) with a function f.sub.reg such
that:
f reg = argmin f ~ .times. i .times. j .times. f .about. .function.
( X i , K j ) - y .function. ( X i , K j ) ##EQU00001##
where Y is a map associating wind characteristic vector X.sub.i and
controller K.sub.j with the corresponding cost, f defines a class
of functions whose parameters are to be optimized so as to minimize
the difference between the predictions of the model and the map.
Function f.sub.reg predicts the value of the cost criterion for the
wind turbine in a closed loop with each controller of the list
under the current wind (measured wind data). It is thus possible to
select the controller K* that is best suited for the current wind
conditions X (measured wind data), by taking the controller that
minimizes the cost criterion according to function f.sub.reg:
K * .function. ( X , f r .times. e .times. g , K list ) = arg
.times. min K j .di-elect cons. K list .times. f reg .function. ( X
, K j ) ##EQU00002##
[0083] According to a second embodiment, the regression can
comprise the following steps:
[0084] i) standardizing the measured wind data;
[0085] ii) performing a polynomial increase in the measured wind
data; and
[0086] iii) performing a linear regression of the polynomially
increased wind data by use of a change in space of the target
value.
[0087] Standardization of the wind data allows the measured wind
data to be brought to a centered normal law.
[0088] The polynomial increase corresponds to multiplying together
the coordinates of the wind data vector up to a certain predefined
degree. For example, data (x1, x2, x3) can be converted to (1, x1,
x2, x3, x1x2, x1x3, x2x3, x12, x22, x32) for a polynomial increase
of degree 2.
[0089] The space change of the target value can be a Box-Cox
transformation allow adding a non-linearity at the output. In
statistics, the Box-Cox transformation is a family of functions
applied to create a monotonic transformation of data using power
functions. Such a transformation allows stabilizing the variance,
to make the data closer to a normal type distribution and to
improve the measurement validity.
[0090] According to a third embodiment, the regression can be based
on a random forest method, a neural network method, a support
vector machine (SVM) method or a Gaussian process method.
[0091] According to one aspect of the invention, classification of
the controllers can directly synthesize a function f.sub.cl
predicting the controller best suited for the current wind
condition X, denoted by K.sup.+=f.sub.cl(X). Function f.sub.cl can
be defined as follows:
f c .times. l = arg .times. min f ~ .times. i .times. h ( f .about.
.function. ( X i ) , arg .times. min K j .di-elect cons. K list
.times. y .function. ( X i , K j ) ) ##EQU00003##
where function h provide a good classification of the
controller:
h .function. ( K a , K b ) = { 1 .times. .times. if .times. .times.
K a .noteq. K b otherwise ##EQU00004##
[0092] According to the initial results, the two methods
(regression and classification) seem to be equivalent. It is noted
that, according to the classification technique used, regression of
a pseudo cost function (fatigue) can be performed. This cost
function is the probability that a controller K is the most
suitable controller under a wind condition X, denoted by p(X,K).
Finally, the result of f.sub.cl is the controller that maximizes
this probability under a wind condition.
[0093] Regression has the advantage of predicting the (fatigue)
cost directly. It is therefore possible to determine a threshold
for controller switch and to limit switching from one controller to
another only to the switches providing a net gain. Classification
has the advantage of directly minimizing the classification error,
and thus limiting risk of taking the wrong controller when
selecting the most suitable controller.
[0094] 4. Controlling the Wind Turbine Quantity
[0095] This step controls online the wind turbine quantity by
applying the controller determined in step 3).
[0096] According to an embodiment corresponding to FIG. 1, the
controller is applied in the feedback loop. The controller accounts
for the regulation error between a regulation setpoint and the
turbine quantity measurement. In this case, the method can comprise
a step of measuring the controlled wind turbine quantity.
[0097] Furthermore, the present invention relates to a system of
controlling a wind turbine quantity, capable of implementing the
method according to any one of the variant combinations
described.
[0098] The control system comprises at least: [0099] means for
storing the controller list and the database constructed by
simulation; [0100] means for wind data measurement; [0101] means
for determining a controller, which uses the controller list and
the database of the means for storage and the wind data
measurements of the means for measuring; and [0102] control means
for applying the determined controller to the wind turbine.
[0103] According to one embodiment of the invention, the means for
deter mining a controller and the means for storing can be a
computer.
[0104] Moreover, the control system may comprise a numerical
simulation computer for constructing the database.
[0105] The advantage of using the method according to the invention
rather than conventional optimal control methods also intended to
minimize a cost criterion is that significant latitude is provided
to the cost criterion. Indeed, the method according to the
invention allows any cost criterion to be used. It is therefore
possible to use precise mechanical fatigue models that can only be
used offline, unlike the conventional MPC (Model Predictive
Control) models that require that the cost criterion can be
continuously re-evaluated online.
[0106] The second advantage is that the method according to the
example can allow optimizing the control over a very complex cost
function using relatively simple control techniques, thereby having
a very low online calculation cost. Furthermore, the control method
according to the invention is intrinsically designed to adapt to
various wind conditions, unlike most other control techniques based
on linear models, which require an additional work of
generalization to the different cases encountered by the wind
turbine.
Example
[0107] Other features and advantages of the control method
according to the invention will be clear from reading the
description of the example hereafter.
[0108] In order to validate the control method according to the
invention, the method was first tested with a wind data set
generated by the TurbSim.TM. wind generator and simulated in closed
loops on the FAST.TM. aeroelastic wind turbine simulator, with 4
controllers. The controllers considered are proportional integral
(PI) IPC controllers corresponding to the one described in Bossanyi
et al. (Bossanyi, 2003). For this example, a CPC controller
mentioned in Jonkman et al. (Jonkman, 2007) provides good
regulation of the rotor speed and power. A PI controller gives,
from the regulation error between the measurement and the desired
value .epsilon.(t), defined as the difference between the measured
quantity to be regulated and the regulation setpoint, the input for
the system to be regulated u(t) as follows:
u(t)=.intg..sub.t.sub.0.sup.tK.sub.I.epsilon.(.tau.)d.tau.+K.sub.p.epsil-
on.(t)
where K.sub.p and K.sub.I are the proportional and integrator
coefficients that define the controller. The parameters of the 4 PI
controllers considered in the example are:
TABLE-US-00001 TABLE 1 Controller K.sub.p K.sub.I 1 4 10.sup.-5
3.2889 10.sup.-5 2 4 10.sup.-5 5.1556 10.sup.-5 3 0.086 0.0031 4
0.0186 0.0066
[0109] The winds used to create the database (learning data) are
non-uniform three-dimensional wind fields with coherent
turbulences. For the learning data, 588 winds were generated with
147 combinations of parameters (average speed, direction, vertical
speed gradient, turbulence intensity).
[0110] To be able to predict fatigue as a function of wind, the
characteristics allowing to explain the fatigue that could be
obtained from wind reconstruction algorithms need to be extracted
from the wind.
[0111] From the TurbSim.TM. wind fields, the wind vector {right
arrow over (V)}(t, y, z)=[u(t, y, z), v(t, y, z), w(t, y, z)].sup.T
is obtained at the time t in the rotor plane where y and z are the
horizontal and vertical coordinates of the field respectively. Let
V be the norm L.sub.2 of vector {right arrow over (V)}(t, y,
z).
[0112] The wind characteristics considered are the average and the
standard deviation over the simulation time (300 seconds), starting
at t0 and ending at tf, of the rotor averaged wind speed RAMS, of
the horizontal and vertical gradients denoted by .delta.y and
.delta.z, and of the pitch and yaw misalignments denoted by
.theta..sub.y and .theta..sub.z. Finally, the rotor averaged
turbulence intensity RATI is calculated for each simulation. The
instantaneous values of RAWS, .delta.y, .delta.z, .theta..sub.y and
.theta..sub.z, as well as the value for the entire simulation of
RATI are mathematically expressed as follows:
RAWS = 1 S .times. .intg. S .times. V .times. d .times. s
##EQU00005## .delta. y .function. ( t ) = 1 S .times. .intg. s
.times. .differential. V .differential. y .times. d .times. s
##EQU00005.2## .delta. z .function. ( t ) = 1 S .times. .intg. S
.times. .differential. V .differential. z .times. d .times. s
##EQU00005.3## .theta. y .function. ( t ) = 1 S .times. .intg. S
.times. tan - 1 .times. w u .times. d .times. s ##EQU00005.4##
.theta. z .function. ( t ) = 1 S .times. .intg. S .times. tan - 1
.times. v u .times. d .times. s ##EQU00005.5## RATI = 1 S .times.
.intg. S .times. .intg. t 0 t f .times. V 2 .times. d .times. t - (
.intg. t 0 t f .times. Vdt ) 2 .intg. t 0 t f .times. V .times. d
.times. t .times. ds ##EQU00005.6##
with S the rotor area and ds=dydz an infinitesimal surface of the
rotor.
[0113] In this example, the machine learning function f has the
following structure, illustrated in FIG. 2 (by way of
non-(imitative example): [0114] standardization STD of data X
(distribution brought to a centered normal law) polynomial increase
(multiplying together the coordinates of the vector up to a certain
degree) [0115] (e.g. (x.sub.1, x.sub.2, x.sub.3).fwdarw.(1,
x.sub.1x.sub.2, x.sub.1x.sub.3, x.sub.2x.sub.3, x.sub.1.sup.2,
x.sub.2.sup.2, x.sub.3.sup.2) for a polynomial increase of degree
2). In the present case, the x are the wind characteristics. We
then obtain data X.sub.poly [0116] linear regression REG from data
X.sub.poly [0117] Box-Cox transformation TBC of the target value
(Box & Cox, 1964), which allows a non-linearity to be added at
the output
[0117] y BoxCox = 1 .lamda. .times. ( y .lamda. - 1 ) ##EQU00006##
[0118] reverse Box-Cox transformation TBC-INV allowing to calculate
the fatigue prediction.
[0119] w* is a vector which results from the optimization of these
coefficients so as to minimize the difference between the
predictions and the map in the Box-Cox space. The equation of shows
how w* is used to predict the cost in the Box-Cox space from
X.sub.poly.
[0120] This regression scheme is performed for each controller
K.sub.j, and all these regressions give function f. We can
therefore write: f(X, K.sub.j)=(X, K.sub.j).
[0121] The first tests show that the substitution model of the cost
evaluation procedure actually allows to predict the cost correctly
on test data not used during learning (database construction). The
regression algorithm has learned on a randomly drawn set without
redelivery of 294 winds, 4 regressions were obtained, one for each
controller.
[0122] The algorithm is tested on 294 randomly drawn wind samples,
without redelivery, not used for learning (database). FIG. 3 shows
the real values VR and the estimated values VE obtained with the
method according to the invention. It is possible to see in FIG. 3
that the algorithm predicts the cost of each simulation correctly,
and the predictions are represented here for the four
simulations.
[0123] To evaluate the quality of the method according to the
invention, two indicators can be used:
R 2 .function. ( K ) = 1 - .nu. .times. ar .function. ( y
.function. ( K ) - y ^ .function. ( K ) ) var .function. ( y
.function. ( K ) ) ##EQU00007## R dec .function. ( K ) = 1 - i
.times. y .function. ( K * , X i ) min K .times. i .times. ( K , X
i ) ##EQU00007.2##
[0124] R.sup.2 gives an indication of the regression algorithm
quality, the closer it is to 1, the higher the quality of the
regression. R.sub.dec gives an approximation of the fatigue
decrease that could be obtained using the best controllers K*
determined by the regression, without accounting for the cost that
could be added by switching from one controller to another.
[0125] Table 2 gives the values of the indicators. Scores R.sup.2
are above 0.9 for each regression. Therefore, the regression method
is of good quality. According to scores R.sub.dec, the algorithm
could indeed allow reduction of the wind turbine cost by at least
20% in relation to the best controller of the set of candidates
alone.
TABLE-US-00002 TABLE 2 Controller R.sup.2 R.sub.dec 1 0.93 23% 2
0.96 35% 3 0.93 36% 4 0.92 26%
* * * * *